Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add miyago9267/pilotfish-codex --skill pilotfish-orchestrationgit clone --depth 1 https://github.com/miyago9267/pilotfish-codexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/miyago9267/pilotfish-codex/pilotfish-orchestration)<a href="https://agentmods.dev/skills/miyago9267/pilotfish-codex/pilotfish-orchestration"><img src="https://agentmods.dev/badge/skills/miyago9267/pilotfish-codex/pilotfish-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/miyago9267/pilotfish-codex/pilotfish-orchestration"><img src="https://agentmods.dev/badge/skills/miyago9267/pilotfish-codex/pilotfish-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01457 |
| Opus 5.5 | $0.00023 | $0.00583 |
| Sonnet 5.5 | $0.00012 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
pilotfish-orchestration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pilotfish orchestration (agy)
Main-session policy. Roles (scout, plan-verifier, security-reviewer,
mech-executor, executor, verifier, security-executor) ignore this skill
and do their task without delegating.
Lifecycle
| Phase | Gate | Delegation |
|---|---|---|
| Discovery | Stabilize the question, allowed scope, evidence format, and stop condition. Read-only. | scout on disjoint evidence surfaces |
| Plan | Main session writes one Plan: outcome, non-goals, scope, program envelope, independent slices. | Fresh plan-verifier on the envelope, then the next executable slice |
| Approval | READY on every required unit, then present the Plan and wait for Miyago's explicit approval. |
Read-only clarification only |
| Execution | Approved contract with scope, exclusive ownership, constraints, done criteria, integration, verification. | mech-executor, executor, or security-executor |
| Verification | Integrated result with an exact claim and concrete acceptance. | Fresh verifier |
If Miyago has switched agy into /plan mode, stay there until approval. If
not, behave as if you were: discovery is read-only and the only thing you write
before approval is the Plan itself (in the reply or a Plan artifact).
Plan gate
- Brief
plan-verifierwith a## Target readiness unitblock (- ID:,- Kind:program envelopeorexecution slice), the full Plan text, and evidence paths. READYis the bare word.REVISEcarries one or more blocks withBlocker:,Evidence:,Minimum revision:,Acceptance check:. Anything else is a protocol failure, not a Plan judgment; re-invoke.- On
REVISE, materially revise and send the unit to a freshplan-verifier. After two automaticREVISEon the same unit, pause and ask Miyago. - Large work: review the envelope, then only the next executable slice. Later slices keep stable IDs, outcomes, and prerequisites until they become current.
- No source writes before explicit approval in a later turn. A broad request, "just start", or auto-approved permissions do not waive this.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago Changed · +30 lines · -14 tokens per session 38a0efe071ff
- 1mo ago Changed · +14 lines 7e1539e81af1
- 1mo ago Changed · +2 lines 819bc8e6d499
- 1mo ago First seen · 79 lines · 72 tokens per session scan A fa6707a59e9c
pilotfish-orchestration is a skill published in the GitHub repository miyago9267/pilotfish-codex (56 stars, last pushed 28d ago), licensed MIT. It adds 58 tokens to every session and 1,457 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…